Now that spring has arrived, families across the country have started the home buying process. However, the average time it takes to close on a house is 50 days, making it a long road to home. Aiming to speed things up, document capture and data analytics company Ephesoft launched Ephesoft Transact for Mortgage this week. This is the California-based company’s first vertical-specific product offering.

The cloud-based platform recognizes and classifies more than 600 mortgage document types. When lenders bundle Ephesoft Transact for Mortgage classification solution with the Ephesoft Transact flagship offering, they can increase mortgage processing speeds. In a statement, Ephesoft said that large organizations will see deployment times reduced by 80%, from several months to just weeks.

Ike Kavas, founder and CEO of Ephesoft, said that the company’s mortgage lendeing and financial services customers will “greatly benefit from the improved speeds provided by the Transact for Mortgage platform.” Kavas added, “We are continuously developing innovative, cost-effective solutions that solve real problems for our customers and with hundreds of different document types to classify, the mortgage processing industry is ideally suited for document capture innovation and automation.”

To get started, mortgage loan processors upload loan documents into a batch, then Ephesoft Transact for Mortgage automatically classifies and separates documents and exports them into the lender’s loan origination system. The system takes appraisal documents, lease agreements, tax returns, bank statements, and other documents necessary in mortgage applications, and deciphers which pages are necessary and which are simply blank pages, cover sheets, invoices, and disclosures. Once documents are classified, the high-value pages are prepared for data extraction and business insights, with the option to apply Ephesoft’s machine learning technology for further analysis.

In the press release, Ephesoft client, Jane Christie, COO of eDocument Solutions, said, “Customers have reported accuracy reports of 90% or higher, loan processing time reduction of 92% and savings of over $100 per loan. The combination of accuracy, consistency and speed for mortgage documents impacts their bottom line and improves customer satisfaction and retention rates.”

At FinovateAsia 2017, Ephesoft demoed how banks can use its cloud services to classify documents, extract their information, and automate business transactions. Last summer, the company earned a $15 million investment from Mercato Partners, its first round of funding since it was founded in 2010. In the fall of 2017, Ephesoft’s developers released version 4.0 of its Transact Mobile SDK.

Document capture and analytics solution developer Ephesoft released version 4.0 of its Transact Mobile SDK this week. The latest version of the technology takes advantage of innovations in everything from deep learning to mobile architecture to give consumers more accuracy and flexibility when it comes to document capture with their mobile devices.

Ike Kavas, Ephesoft CTO, highlighted the way the enhancements paved the way for better, easier-to-read images. “For example, deep learning is employed in our live-edge detection functionality that has historically been a challenge for identifying document boundaries on mobile devices,” Kavas explained. “This new approach captures clearer images.” Deep learning provides a better solution than typical bitonal image recognition because deep learning has predictive capabilities. The system is able to predict edges, for example, which along with the ability to extract text and numbers, makes it ideal for credit card recognition.

(left to right): Alastair Allars (Success Engineer) and Ike Kavas (CTO) demonstrating Ephesoft Transact Cloud Service at FinovateAsia 2017 in Hong Kong.

Ephesoft’s Transact Mobile SDK 4.0 also includes image auto-capture and auto-alignment, making images scanned by mobile devices comparable to those created by topline scanners. Online and offline batch processing enables users to do character recognition, document classification, and data extraction when offline. Version 4.0 also features security enhancements such as a private directory for storing images temporarily when using mobile devices (the directory is erased when the application is closed). The solution uses ARM 64-bit architecture to improve memory capacity for more powerful processing, and also includes image enhancement tools, simple barcode interpretation, and on-device OCR.

Founded in 2010 and headquartered in Laguna Hills, California, Ephesoft demonstrated its Ephesoft Transact Cloud Service at FinovateAsia 2017 earlier this month. The company has raised $15 million in funding, completing a Series A round led by Mercato Partners in August. Also in August, Ephesoft announced that New Zealand’s Motor Trade Finance (MTF) would use Ephesoft’s Transact platform. An Inc. 500 company with customers in more than 30 countries. Ephesoft released its analytics and business intelligence platform, Insight 3.1, in October. Don Field is CEO.